unix_utils 0.0.2

data/.gitignore

@@ -0,0 +1,18 @@
+*.gem
+*.rbc
+.bundle
+.config
+.yardoc
+Gemfile.lock
+InstalledFiles
+_yardoc
+coverage
+doc/
+lib/bundler/man
+pkg
+rdoc
+spec/reports
+test/tmp
+test/version_tmp
+tmp
+.DS_Store

data/Gemfile

@@ -0,0 +1,7 @@
+source :rubygems
+
+gemspec
+
+# development dependencies
+gem 'minitest'
+gem 'minitest-reporters'

data/History.txt

@@ -0,0 +1,9 @@
+== 0.0.2 / 2012-02-16
+
+* Bug fixes
+
+  * Fix use of splat internally so that it actually runs in MRI 1.8.7 and JRuby
+
+== 0.0.1 / 2012-02-16 (yanked!)
+
+* Birthday!

data/README.markdown

@@ -0,0 +1,77 @@
+# unix_utils
+
+Like FileUtils, but provides zip, unzip, bzip2, bunzip2, tar, untar, sed, du, md5sum, shasum, cut, head, tail, wc, unix2dos, dos2unix, iconv, curl, perl, etc.
+
+Works in MRI 1.8.7+, MRI 1.9.2+, and JRuby 1.6.7+
+
+## What to expect
+
+For commands like zip, untar, sed, head, cut, dos2unix, etc.:
+
+1. Just returns a path to the output, randomly named, located in the system tmp dir (`UnixUtils.unzip('kittens.zip)` → `'/tmp/unix_utils-129392301-kittens'`)
+2. Never touches the input
+3. Sticks a useful file extension on the output, if applicable (`UnixUtils.tar('puppies/')` → `'/tmp/unix_utils-99293192-puppies.tar'`)
+
+For commands like du, md5sum, shasum, etc.:
+
+1. Just returns the good stuff (the checksum, for example, not the filename that is listed after it in the standard command output)
+2. Never touches the input
+
+## Philosophy
+
+Use a subprocess to perform a big task and then get out of memory.
+
+## But I can just spawn these myself
+
+This lib was created to ease the pain of remembering command options for Gentoo, deciding which spawning method to use, possibly handling pipes...
+
+    require 'tmpdir'
+    destdir = File.join(Dir.tmpdir, "kittens_#{Kernel.rand(1e11)}")
+    require 'open3'
+    Open3.popen3('unzip', '-q', '-n', 'kittens.zip, '-d', destdir) do |stdin, stdout, stderr|
+      stdin.close
+      @error_message = stderr.read
+    end
+
+is replaced safely with
+
+    destdir = UnixUtils.unzip 'kittens.zip'
+
+## But I can just use `Digest::SHA256`
+
+This will load an entire file into memory before it can be processed...
+
+    require 'digest'
+    str = Digest::SHA256.hexdigest File.read('kittens.zip')
+
+... so you're really replacing this ...
+
+    sha256 = Digest::SHA256.new
+    File.open('kittens.zip', 'r') do |f|
+      while chunk = f.read(4_194_304)
+        sha256 << chunk
+      end
+    end
+    str = sha256.hexdigest
+
+You get the same low memory footprint with
+
+    str = UnixUtils.shasum('kittens.zip', 256)
+
+## Compatibility
+
+Uses `open3` because it's in the Ruby stdlib and is consistent across MRI and JRuby.
+
+## Where it's used
+
+* [Brighter Planet Reference Data web service](http://data.brighterplanet.com)
+* [Brighter Planet Emission Estimate web service](http://impact.brighterplanet.com) aka CM1
+* [`remote_table` library](https://github.com/seamusabshere/remote_table)
+
+## Authors
+
+* Seamus Abshere <seamus@abshere.net>
+
+## Copyright
+
+Copyright (c) 2012 Brighter Planet. See LICENSE for details.

data/Rakefile

@@ -0,0 +1,12 @@
+#!/usr/bin/env rake
+require "bundler/gem_tasks"
+
+require 'rake'
+require 'rake/testtask'
+Rake::TestTask.new(:test) do |test|
+  test.libs << 'lib' << 'test'
+  test.pattern = 'test/**/test_*.rb'
+  test.verbose = true
+end
+
+task :default => :test

data/lib/unix_utils.rb

@@ -0,0 +1,276 @@
+require 'fileutils'
+require 'tmpdir'
+require 'uri'
+require 'open3'
+
+require "unix_utils/version"
+
+module UnixUtils
+
+  def self.curl(url, form_data = nil)
+    outfile = tmp_path url
+    if url.start_with?('/') or url.start_with?('file://')
+      # deal with local files
+      ::FileUtils.cp url.delete('file://'), path
+      return outfile
+    end
+    uri = ::URI.parse url
+    argv = [ 'curl', '--location', '--show-error', '--silent', '--compressed', '--header', 'Expect: ' ]
+    if form_data
+      argv += [ '--data', form_data ]
+    end
+    argv += [ uri.to_s, '--output', outfile ]
+    spawn argv
+    outfile
+  end
+
+  #--
+  # most platforms
+  # $ openssl dgst -sha256 .bash_profile 
+  # SHA256(.bash_profile)= ae12206aaa35dc96273ed421f4e85ca26a1707455e3cc9f054c7f5e2e9c53df6
+  # ubuntu 11.04
+  # $ shasum -a 256 --portable .mysql_history 
+  # 856aa27deb0b80b41031c2ddf722af28ba2a8c4999ff9cf2d45f33bc67d992ba ?.mysql_history
+  # fedora 7
+  # $ sha256sum --binary .bash_profile 
+  # 01b1210962b3d1e5e1ccba26f93d98efbb7b315b463f9f6bdb40ab496728d886 *.bash_profile
+  def self.shasum(infile, algorithm)
+    if available?('shasum')
+      argv = ['shasum', '--binary', '-a', algorithm.to_s, infile]
+      stdout = spawn argv
+      stdout.strip.split(' ').first
+    else
+      argv = ['openssl', 'dgst', "-sha#{algorithm}", infile]
+      stdout = spawn argv
+      stdout.strip.split(' ').last
+    end
+  end
+  
+  #--
+  # os x 10.6.8; most platforms
+  # $ openssl dgst -md5 .bashrc 
+  # MD5(.bashrc)= 88f464fb6d1d6fe9141135248bf7b265
+  # ubuntu 11.04; fedora 7; gentoo
+  # $ md5sum --binary .mysql_history 
+  # 8d01e54ab8142d6786850e22d55a1b6c *.mysql_history  
+  def self.md5sum(infile)
+    if available?('md5sum')
+      argv = ['md5sum', '--binary', infile]
+      stdout = spawn argv
+      stdout.strip.split(' ').first
+    else
+      argv = ['openssl', 'dgst', '-md5', infile]
+      stdout = spawn argv
+      stdout.strip.split(' ').last
+    end
+  end
+    
+  def self.du(srcdir)
+    argv = ['du', srcdir]
+    stdout = spawn argv
+    stdout.strip.split(/\s+/).first.to_i
+  end
+  
+  def self.wc(infile)
+    argv = ['wc', infile]
+    stdout = spawn argv
+    stdout.strip.split(/\s+/)[0..2].map { |s| s.to_i }
+  end
+
+  # --
+  
+  def self.unzip(infile)
+    destdir = tmp_path infile
+    ::FileUtils.mkdir destdir
+    argv = ['unzip', '-qq', '-n', infile, '-d', destdir]
+    spawn argv
+    destdir
+  end
+
+  def self.untar(infile)
+    destdir = tmp_path infile
+    ::FileUtils.mkdir destdir
+    argv = ['tar', '-xf', infile, '-C', destdir]
+    spawn argv
+    destdir
+  end
+
+  def self.gunzip(infile)
+    outfile = tmp_path infile
+    argv = ['gunzip', '--stdout', infile]
+    spawn argv, :write_to => outfile
+    outfile
+  end
+
+  def self.bunzip2(infile)
+    outfile = tmp_path infile
+    argv = ['bunzip2', '--stdout', infile,]
+    spawn argv, :write_to => outfile
+    outfile
+  end
+
+  # --
+
+  def self.bzip2(infile)
+    outfile = tmp_path infile, '.bz2'
+    argv = ['bzip2', '--keep', '--stdout', infile]
+    spawn argv, :write_to => outfile
+    outfile
+  end
+  
+  def self.tar(srcdir)
+    outfile = tmp_path srcdir, '.tar'
+    argv = ['tar', '-cf', outfile, '-C', srcdir, '.']
+    spawn argv
+    outfile
+  end
+
+  def self.zip(srcdir)
+    outfile = tmp_path srcdir, '.zip'
+    argv = ['zip', '-rq', outfile, '.']
+    spawn argv, :chdir => srcdir
+    outfile
+  end
+  
+  def self.gzip(infile)
+    outfile = tmp_path infile, '.gz'
+    argv = ['gzip', '--stdout', infile]
+    spawn argv, :write_to => outfile
+    outfile
+  end
+  
+  # --
+  
+  def self.awk(infile, *expr)
+    outfile = tmp_path infile
+    bin = available?('gawk') ? 'gawk' : 'awk'
+    argv = [bin, expr, infile].flatten
+    spawn argv, :write_to => outfile
+    outfile
+  end
+  
+  # Yes, this is a very limited use of perl.
+  def self.perl(infile, *expr)
+    outfile = tmp_path infile
+    argv = [ 'perl', expr.map { |e| ['-pe', e] } ].flatten
+    spawn argv, :read_from => infile, :write_to => outfile
+    outfile
+  end
+  
+  def self.unix2dos(infile)
+    if available?('gawk') or available?('awk')
+      awk infile, '{ sub(/\r/, ""); printf("%s\r\n", $0) }'
+    else
+      perl infile, 's/\r\n|\n|\r/\r\n/g'
+    end
+  end
+  
+  def self.dos2unix(infile)
+    if available?('gawk') or available?('awk')
+      awk infile, '{ sub(/\r/, ""); printf("%s\n", $0) }'
+    else
+      perl infile, 's/\r\n|\n|\r/\n/g'
+    end
+  end
+
+  def self.sed(infile, *expr)
+    outfile = tmp_path infile
+    bin = available?('gsed') ? 'gsed' : 'sed'
+    argv = [ bin, expr.map { |e| ['-e', e] } ].flatten
+    spawn argv, :read_from => infile, :write_to => outfile
+    outfile
+  end
+
+  def self.tail(infile, lines)
+    outfile = tmp_path infile
+    argv = ['tail', '-n', lines.to_s, infile]
+    spawn argv, :write_to => outfile
+    outfile
+  end
+  
+  def self.head(infile, lines)
+    outfile = tmp_path infile
+    argv = ['head', '-n', lines.to_s, infile]
+    spawn argv, :write_to => outfile
+    outfile
+  end
+
+  # specify character_positions as a string like "3-5" or "3,9-10"
+  def self.cut(infile, character_positions)
+    outfile = tmp_path infile
+    argv = ['cut', '-c', character_positions, infile]
+    spawn argv, :write_to => outfile
+    outfile
+  end
+
+  def self.iconv(infile, to, from)
+    outfile = tmp_path infile
+    argv = ['iconv', '-t', to, '-f', from, infile]
+    spawn argv, :write_to => outfile
+    outfile
+  end
+  
+  def self.available?(bin) # :nodoc:
+    bin = bin.to_s
+    return @@available_query[bin] if defined?(@@available_query) and @@available_query.is_a?(::Hash) and @@available_query.has_key?(bin)
+    @@available_query ||= {}
+    @@available_query[bin] = ::Kernel.system 'which', '-s', bin
+  end
+
+  def self.tmp_path(ancestor, extname = nil) # :nodoc:
+    extname ||= ::File.extname ancestor
+    basename = ::File.basename ancestor.sub(/^unix_utils-[0-9]+-/, '').gsub(/\W+/, '_')
+    name = basename + extname
+    ::Kernel.srand
+    ::File.join ::Dir.tmpdir, "unix_utils-#{::Kernel.rand(1e11)}-#{name}"
+  end
+
+  def self.spawn(argv, options = {}) # :nodoc:
+    if options[:chdir]
+      old_pwd = ::Dir.pwd
+      ::Dir.chdir options[:chdir]
+    end
+    
+    whole_stdout = nil
+    whole_stderr = nil
+
+    ::Open3.popen3(*argv) do |stdin, stdout, stderr|
+      # deal with STDIN
+      if options[:read_from]
+        ::File.open(options[:read_from], 'r') do |in_f|
+          while chunk = in_f.read(4_194_304)
+            stdin.write chunk
+          end
+        end
+      end
+      stdin.close
+
+      # deal with STDOUT
+      if options[:write_to]
+        ::File.open(options[:write_to], 'wb') do |out_f|
+          while chunk = stdout.read(4_194_304)
+            out_f.write chunk
+          end
+        end
+        whole_stdout = "Redirected to #{options[:write_to]}"
+      else
+        whole_stdout = stdout.read
+      end
+      
+      # deal with STDERR
+      whole_stderr = stderr.read
+    end
+
+    unless whole_stderr.empty?
+      $stderr.puts "[unix_utils] `#{argv.join(' ')}` STDERR:"
+      $stderr.puts whole_stderr
+    end
+
+    whole_stdout
+
+  ensure
+    if options[:chdir]
+      ::Dir.chdir old_pwd
+    end
+  end
+end

data/lib/unix_utils/version.rb

@@ -0,0 +1,3 @@
+module UnixUtils
+  VERSION = "0.0.2"
+end

data/test/helper.rb

@@ -0,0 +1,73 @@
+require 'rubygems'
+require 'bundler/setup'
+
+require 'minitest/spec'
+require 'minitest/autorun'
+require 'minitest/reporters'
+MiniTest::Unit.runner = MiniTest::SuiteRunner.new
+MiniTest::Unit.runner.reporters << MiniTest::Reporters::SpecReporter.new
+
+$LOAD_PATH.unshift(File.dirname(__FILE__))
+$LOAD_PATH.unshift(File.join(File.dirname(__FILE__), '..', 'lib'))
+require 'unix_utils'
+
+require 'fileutils'
+require 'tmpdir'
+require 'tempfile'
+
+module TestHelper
+  def assert_does_not_touch(method_id, *args)
+    infile_or_srcdir = args.first
+    mtime = File.mtime infile_or_srcdir
+    kind = File.file?(infile_or_srcdir) ? :file : :directory
+    case kind
+    when :file
+      checksum = UnixUtils.shasum infile_or_srcdir, 256
+    when :directory
+      size = UnixUtils.du infile_or_srcdir
+    end
+    destdir = UnixUtils.send(*([method_id] + args))
+    safe_delete destdir
+    File.mtime(infile_or_srcdir).must_equal mtime
+    case kind
+    when :file
+      UnixUtils.shasum(infile_or_srcdir, 256).must_equal checksum
+    when :directory
+      UnixUtils.du(infile_or_srcdir).must_equal size
+    end
+  end
+  
+  def assert_unpack_dir(method_id, infile)
+    destdir = UnixUtils.send method_id, infile
+    File.directory?(destdir).must_equal true
+    Dir.entries(destdir).must_equal %w{ . .. hello_world.txt hello_world.xml }
+    File.dirname(destdir).start_with?(Dir.tmpdir).must_equal true
+    safe_delete destdir
+  end
+  
+  def assert_unpack_file(method_id, infile)
+    outfile = UnixUtils.send method_id, infile
+    File.file?(outfile).must_equal true
+    `file #{outfile}`.chomp.must_match %r{text}
+    File.dirname(outfile).start_with?(Dir.tmpdir).must_equal true
+    safe_delete outfile
+  end
+    
+  def assert_pack(method_id, infile)
+    outfile = UnixUtils.send method_id, infile
+    File.file?(outfile).must_equal true
+    `file #{outfile}`.chomp.must_match %r{\b#{method_id.to_s.downcase}\b}
+    File.dirname(outfile).start_with?(Dir.tmpdir).must_equal true
+    safe_delete outfile
+  end
+  
+  def safe_delete(path)
+    path = File.expand_path path
+    raise "Refusing to rm -rf #{path} because it's not in #{Dir.tmpdir}" unless File.dirname(path).start_with?(Dir.tmpdir)
+    FileUtils.rm_rf path
+  end
+end
+
+class MiniTest::Spec
+  include TestHelper
+end

data/test/target/directory/hello_world.txt

@@ -0,0 +1 @@
+hello world

data/test/target/directory/hello_world.xml

@@ -0,0 +1 @@
+<b>hello world</b>

data/test/target/iso-8859-1.txt

@@ -0,0 +1 @@
+Hola, �c�mo est�s?

data/test/target/utf8.txt

@@ -0,0 +1 @@
+Hola, ¿cómo estás?

data/test/test_unix_utils.rb

@@ -0,0 +1,383 @@
+# encoding: UTF-8
+require 'helper'
+
+describe UnixUtils do
+  before do
+    @old_pwd = Dir.pwd
+    Dir.chdir File.expand_path('../target', __FILE__)
+  end
+  
+  after do
+    Dir.chdir @old_pwd
+  end
+  
+  describe :curl do
+    it "downloads to a temp file" do
+      outfile = UnixUtils.curl('http://brighterplanet.com')
+      File.read(outfile).must_match %r{sustain}i
+      safe_delete outfile
+    end
+  end
+  
+  describe :shasum do
+    it "checksums a file with SHA-1" do
+      UnixUtils.shasum('directory.zip', 1).must_equal 'c0abb36c923ed7bf87ebb8d7097cb8e264e528d2'
+    end
+    it "checksums a file with SHA-256" do
+      UnixUtils.shasum('directory.zip', 256).must_equal '661af2b7b0993088263228b071b649a88d82a6a655562162c32307d1e127f27a'
+    end
+  end
+  
+  describe :md5sum do
+    it "checksums a file" do
+      UnixUtils.md5sum('directory.zip').must_equal 'd6e15da798ae19551da6c49ec09afaef'
+    end
+  end
+
+  describe :du do
+    it "calculates the size of a directory in bytes" do
+      UnixUtils.du('directory').must_equal 16
+    end
+  end
+  
+  describe :unzip do
+    before do
+      @infile = 'directory.zip'
+      @anonymous_infile = 'directory-really-a-z_i_p-shh'
+    end
+    it "unpacks a DIRECTORY located in the tmp directory" do
+      assert_unpack_dir :unzip, @infile
+    end
+    it "accepts unsemantic filenames" do
+      assert_unpack_dir :unzip, @anonymous_infile
+    end
+    it "does not touch the infile" do
+      assert_does_not_touch :unzip, @infile
+    end
+  end
+  
+  describe :untar do
+    before do
+      @infile = 'directory.tar'
+      @anonymous_infile = 'directory-really-a-t_a_r-shh'
+    end
+    it "unpacks a DIRECTORY located in the tmp directory" do
+      assert_unpack_dir :untar, @infile
+    end
+    it "accepts unsemantic filenames" do
+      assert_unpack_dir :untar, @anonymous_infile
+    end
+    it "does not touch the infile" do
+      assert_does_not_touch :untar, @infile
+    end
+  end
+  
+  describe :bunzip2 do
+    before do
+      @infile = 'file.bz2'
+      @anonymous_infile = 'file-really-a-b_z_2-shh'
+    end
+    it "unpacks a FILE located in the tmp directory" do
+      assert_unpack_file :bunzip2, @infile
+    end
+    it "accepts unsemantic filenames" do
+      assert_unpack_file :bunzip2, @anonymous_infile
+    end
+    it "does not touch the infile" do
+      assert_does_not_touch :bunzip2, @infile
+    end
+  end
+  
+  describe :gunzip do
+    before do
+      @infile = 'file.gz'
+      @anonymous_infile = 'file-really-a-g_z-shh'
+    end
+    it "unpacks a FILE located in the tmp directory" do
+      assert_unpack_file :gunzip, @infile
+    end
+    it "accepts unsemantic filenames" do
+      assert_unpack_file :gunzip, @anonymous_infile
+    end
+    it "does not touch the infile" do
+      assert_does_not_touch :gunzip, @infile
+    end
+  end
+  
+  describe :bzip2 do
+    before do
+      @infile = 'directory.tar'
+    end
+    it "packs a FILE to a FILE in the tmp directory" do
+      assert_pack :bzip2, @infile
+    end
+    it "does not touch the infile" do
+      assert_does_not_touch :bzip2, @infile
+    end
+    it "sticks on a useful extension" do
+      outfile = UnixUtils.bzip2 @infile
+      File.extname(outfile).must_equal '.bz2'
+      safe_delete outfile
+    end
+  end
+  
+  describe :gzip do
+    before do
+      @infile = 'directory.tar'
+    end
+    it "packs a FILE to a FILE in the tmp directory" do
+      assert_pack :gzip, @infile
+    end
+    it "does not touch the infile" do
+      assert_does_not_touch :gzip, @infile
+    end
+    it "sticks on a useful extension" do
+      outfile = UnixUtils.gzip @infile
+      File.extname(outfile).must_equal '.gz'
+      safe_delete outfile
+    end
+  end
+  
+  describe :zip do
+    before do
+      @srcdir = 'directory'
+    end
+    it "packs a DIRECTORY to a FILE in the tmp directory" do
+      assert_pack :zip, @srcdir
+    end
+    it "does not touch the infile" do
+      assert_does_not_touch :zip, @srcdir
+    end
+    it "sticks on a useful extension" do
+      outfile = UnixUtils.zip @srcdir
+      File.extname(outfile).must_equal '.zip'
+      safe_delete outfile
+    end
+  end
+  
+  describe :tar do
+    before do
+      @srcdir = 'directory'
+    end
+    it "packs a DIRECTORY to a FILE in the tmp directory" do
+      assert_pack :tar, @srcdir
+    end
+    it "does not touch the infile" do
+      assert_does_not_touch :tar, @srcdir
+    end
+    it "sticks on a useful extension" do
+      outfile = UnixUtils.tar @srcdir
+      File.extname(outfile).must_equal '.tar'
+      safe_delete outfile
+    end
+  end
+  
+  describe :perl do
+    before do
+      @f = Tempfile.new('perl.txt')
+      @f.write "bad\n"*10
+      @f.flush
+      @infile = @f.path
+    end
+    after do
+      @f.close
+    end
+    it "processes a file" do
+      outfile = UnixUtils.perl(@infile, 's/bad/good/g')
+      File.read(outfile).must_equal "good\n"*10
+      safe_delete outfile
+    end
+    it "does not touch the infile" do
+      assert_does_not_touch :perl, @infile, 's/bad/good/g'
+    end
+    it "keeps the original extname" do
+      outfile = UnixUtils.perl(@infile, 's/bad/good/g')
+      File.extname(outfile).must_equal File.extname(@infile)
+      safe_delete outfile
+    end
+  end
+  
+  describe :awk do
+    before do
+      @f = Tempfile.new('awk.txt')
+      @f.write "bad\n"*10
+      @f.flush
+      @infile = @f.path
+    end
+    after do
+      @f.close
+    end
+    it "processes a file" do
+      outfile = UnixUtils.awk(@infile, '{gsub(/bad/, "good"); print}')
+      File.read(outfile).must_equal "good\n"*10
+      safe_delete outfile
+    end
+    it "does not touch the infile" do
+      assert_does_not_touch :awk, @infile, '{gsub(/bad/, "good"); print}'
+    end
+    it "keeps the original extname" do
+      outfile = UnixUtils.awk(@infile, '{gsub(/bad/, "good"); print}')
+      File.extname(outfile).must_equal File.extname(@infile)
+      safe_delete outfile
+    end
+  end
+  
+  describe :unix2dos do
+    before do
+      @f = Tempfile.new('unix2dos.txt')
+      @f.write "unix\n"*5
+      @f.write "dos\r\n"*5
+      @f.flush
+      @infile = @f.path
+    end
+    after do
+      @f.close
+    end
+    it 'converts newlines' do
+      outfile = UnixUtils.unix2dos @infile
+      File.read(outfile).must_equal("unix\r\n"*5 + "dos\r\n"*5)
+      safe_delete outfile
+    end
+  end
+  
+  describe :dos2unix do
+    before do
+      @f = Tempfile.new('dos2unix.txt')
+      @f.write "dos\r\n"*5
+      @f.write "unix\n"*5
+      @f.flush
+      @infile = @f.path
+    end
+    after do
+      @f.close
+    end
+    it 'converts newlines' do
+      outfile = UnixUtils.dos2unix @infile
+      File.read(outfile).must_equal("dos\n"*5 + "unix\n"*5)
+      safe_delete outfile
+    end
+  end
+  
+  describe :wc do
+    before do
+      @f = Tempfile.new('wc.txt')
+      @f.write "dos line\r\n"*5
+      @f.write "unix line\n"*5
+      @f.flush
+      @infile = @f.path
+    end
+    after do
+      @f.close
+    end
+    it 'counts lines, words, and bytes' do
+      UnixUtils.wc(@infile).must_equal [5+5, 10+10, 50+50]
+    end
+  end
+
+  describe :sed do
+    before do
+      @f = Tempfile.new('sed.txt')
+      @f.write "bad\n"*10
+      @f.flush
+      @infile = @f.path
+    end
+    after do
+      @f.close
+    end
+    it "processes a file" do
+      outfile = UnixUtils.sed(@infile, 's/bad/good/g')
+      File.read(outfile).must_equal "good\n"*10
+      safe_delete outfile
+    end
+    it "does not touch the infile" do
+      assert_does_not_touch :sed, @infile, 's/bad/good/g'
+    end
+    it "keeps the original extname" do
+      outfile = UnixUtils.sed(@infile, 's/bad/good/g')
+      File.extname(outfile).must_equal File.extname(@infile)
+      safe_delete outfile
+    end
+    
+  end
+
+  describe :tail do
+    before do
+      @a2z = ('a'..'z').to_a
+      @f = Tempfile.new('tail.txt')
+      @f.write @a2z.join("\n")
+      @f.flush
+      @infile = @f.path
+    end
+    after do
+      @f.close
+    end
+    it 'gets last three lines' do
+      outfile = UnixUtils.tail(@infile, 3)
+      File.read(outfile).must_equal @a2z.last(3).join("\n")
+      safe_delete outfile
+    end
+    it 'gets trailing lines starting with the third line (inclusive)' do
+      outfile = UnixUtils.tail(@infile, '+3')
+      File.read(outfile).must_equal @a2z[2..-1].join("\n")
+      safe_delete outfile
+    end
+  end
+  
+  describe :head do
+    before do
+      @a2z = ('a'..'z').to_a
+      @f = Tempfile.new('head.txt')
+      @f.write @a2z.join("\n")
+      @f.flush
+      @infile = @f.path
+    end
+    after do
+      @f.close
+    end
+    it 'gets first three lines' do
+      outfile = UnixUtils.head(@infile, 3)
+      File.read(outfile).must_equal(@a2z.first(3).join("\n") + "\n")
+      safe_delete outfile
+    end
+  end
+  
+  describe :cut do
+    before do
+      @a2z = ('a'..'z').to_a
+      @f = Tempfile.new('cut.txt')
+      10.times do
+        @f.write(@a2z.join + "\n")
+      end
+      @f.flush
+      @infile = @f.path
+    end
+    after do
+      @f.close
+    end
+    it 'cuts out character positions' do
+      outfile = UnixUtils.cut(@infile, '1,12,13,15,19,20')
+      almosts = (0..9).map { |i| 'almost' }.join("\n") + "\n"
+      File.read(outfile).must_equal almosts
+      safe_delete outfile
+    end
+    it 'cuts out character ranges (inclusive)' do
+      outfile = UnixUtils.cut(@infile, '3-6')
+      cdefs = (0..9).map { |i| 'cdef' }.join("\n") + "\n"
+      File.read(outfile).must_equal cdefs
+      safe_delete outfile
+    end
+  end
+  
+  describe :iconv do
+    it 'converts files from utf-8 to latin1' do
+      outfile = UnixUtils.iconv('utf8.txt', 'ISO-8859-1', 'UTF-8')
+      UnixUtils.md5sum(outfile).must_equal UnixUtils.md5sum('iso-8859-1.txt')
+      safe_delete outfile
+    end
+    it 'converts files from latin1 to utf-8' do
+      outfile = UnixUtils.iconv('iso-8859-1.txt', 'UTF-8', 'ISO-8859-1')
+      UnixUtils.md5sum(outfile).must_equal UnixUtils.md5sum('utf8.txt')
+      safe_delete outfile
+    end
+  end
+end

data/unix_utils.gemspec

@@ -0,0 +1,18 @@
+# -*- encoding: utf-8 -*-
+require File.expand_path('../lib/unix_utils/version', __FILE__)
+
+Gem::Specification.new do |gem|
+  gem.authors       = ["Seamus Abshere"]
+  gem.email         = ["seamus@abshere.net"]
+  desc = %q{Like FileUtils, but provides zip, unzip, bzip2, bunzip2, tar, untar, sed, du, md5sum, shasum, cut, head, tail, wc, unix2dos, dos2unix, iconv, curl, perl, etc.}
+  gem.description   = desc
+  gem.summary       = desc
+  gem.homepage      = "https://github.com/seamusabshere/unix_utils"
+
+  gem.executables   = `git ls-files -- bin/*`.split("\n").map{ |f| File.basename(f) }
+  gem.files         = `git ls-files`.split("\n")
+  gem.test_files    = `git ls-files -- {test,spec,features}/*`.split("\n")
+  gem.name          = "unix_utils"
+  gem.require_paths = ["lib"]
+  gem.version       = UnixUtils::VERSION
+end

metadata

@@ -0,0 +1,86 @@
+--- !ruby/object:Gem::Specification
+name: unix_utils
+version: !ruby/object:Gem::Version
+  version: 0.0.2
+  prerelease: 
+platform: ruby
+authors:
+- Seamus Abshere
+autorequire: 
+bindir: bin
+cert_chain: []
+date: 2012-02-17 00:00:00.000000000 Z
+dependencies: []
+description: Like FileUtils, but provides zip, unzip, bzip2, bunzip2, tar, untar,
+  sed, du, md5sum, shasum, cut, head, tail, wc, unix2dos, dos2unix, iconv, curl, perl,
+  etc.
+email:
+- seamus@abshere.net
+executables: []
+extensions: []
+extra_rdoc_files: []
+files:
+- .gitignore
+- Gemfile
+- History.txt
+- README.markdown
+- Rakefile
+- lib/unix_utils.rb
+- lib/unix_utils/version.rb
+- test/helper.rb
+- test/target/directory-really-a-t_a_r-shh
+- test/target/directory-really-a-z_i_p-shh
+- test/target/directory.tar
+- test/target/directory.zip
+- test/target/directory/hello_world.txt
+- test/target/directory/hello_world.xml
+- test/target/file-really-a-b_z_2-shh
+- test/target/file-really-a-g_z-shh
+- test/target/file.bz2
+- test/target/file.gz
+- test/target/iso-8859-1.txt
+- test/target/utf8.txt
+- test/test_unix_utils.rb
+- unix_utils.gemspec
+homepage: https://github.com/seamusabshere/unix_utils
+licenses: []
+post_install_message: 
+rdoc_options: []
+require_paths:
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement
+  none: false
+  requirements:
+  - - ! '>='
+    - !ruby/object:Gem::Version
+      version: '0'
+required_rubygems_version: !ruby/object:Gem::Requirement
+  none: false
+  requirements:
+  - - ! '>='
+    - !ruby/object:Gem::Version
+      version: '0'
+requirements: []
+rubyforge_project: 
+rubygems_version: 1.8.15
+signing_key: 
+specification_version: 3
+summary: Like FileUtils, but provides zip, unzip, bzip2, bunzip2, tar, untar, sed,
+  du, md5sum, shasum, cut, head, tail, wc, unix2dos, dos2unix, iconv, curl, perl,
+  etc.
+test_files:
+- test/helper.rb
+- test/target/directory-really-a-t_a_r-shh
+- test/target/directory-really-a-z_i_p-shh
+- test/target/directory.tar
+- test/target/directory.zip
+- test/target/directory/hello_world.txt
+- test/target/directory/hello_world.xml
+- test/target/file-really-a-b_z_2-shh
+- test/target/file-really-a-g_z-shh
+- test/target/file.bz2
+- test/target/file.gz
+- test/target/iso-8859-1.txt
+- test/target/utf8.txt
+- test/test_unix_utils.rb
+has_rdoc: